Stars
A Library for Advanced Deep Time Series Models for General Time Series Analysis.
Official implementation for "TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables" (NeurIPS 2024)
About model release for "Sundial: A Family of Highly Capable Time Series Foundation Models" (ICML 2025 Oral)
[ICCV 2023] A large-scale high-resolution dataset satisfies all important data features about document shadow, covers a large number of document shadow images.
[ECCV2020] A super-resolution dataset of paired LR-HR scene text images
PyTorch Implementation of Google Research's MetNet and MetNet-2
Solar Forecasting using PVNet on Open Data
Application for running PVNet in production
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Code for "Neural approximation to the stochastic differential equation"
A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.
Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"
Code for "Neural Stochastic Differential Gaems for Time-series Analysis"
Translate from: https://jax.readthedocs.io/en/latest
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.